Skip to main content

Python File Tool

This tool loads a python file and extracts function names, arguments and descriptions automatically. This tool is particular useful for automatically creating custom Tool Specs when you already have well documented python functions.

Usage

This tool has more extensive example usage documented in a Jupyter notebook here

Here's an example usage of the PythonFileToolSpec.

from llama_index.tools.python_file import PythonFileToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

pyfile = PythonFileToolSpec("./numpy_linalg.py")

agent = FunctionAgent(
    tools=pyfile.to_tool_list(),
    llm=OpenAI(model="gpt-4.1"),
)

print(
    await agent.run(
        """Load the eig, transpose and solve functions from the python file,
and then write a function definition using only builtin python types (List, float, Tuple)
with a short 5-10 line doc string tool prompts for the functions that only has a small description and arguments
"""
    )
)

function_definitions: Get all of the function definitions from the Python file get_function: Get a specific function definition from the Python file get_functions: Get a list of functions from the python file

This loader is designed to be used as a way to load data as a Tool in a Agent.

Metadata

Release files for llama-index-tools-python-file 0.6.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llama-index-tools-python-file 0.6.0
File Size Uploaded Provenance Actions
llama_index_tools_python_file-0.6.0.tar.gz 4.0 kB Without provenance Details for llama_index_tools_python_file-0.6.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llama-index-tools-python-file 0.6.0
File Interpreter ABI Platform Actions
llama_index_tools_python_file-0.6.0-py3-none-any.whl Python 3 none any Details for llama_index_tools_python_file-0.6.0-py3-none-any.whl

Total release size: 7.8 kB

Release files / llama_index_tools_python_file-0.6.0.tar.gz

Download URL llama_index_tools_python_file-0.6.0.tar.gz
Size 4.0 kB
Tags Source
SHA-256 checksum
How to use checksums
210d5c170b3cfa35258405bd86e7f28651cf76199f002d72670e64fcb794ba03
BLAKE2b-256 checksum
How to use checksums
37e34a86fd97cbc9fad61c268148590c31f1d70c1e7e1337a4bb3433e47940d9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / llama_index_tools_python_file-0.6.0-py3-none-any.whl

Download URL llama_index_tools_python_file-0.6.0-py3-none-any.whl
Size 3.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9d18c7781f242b3e18d13680f937ac99dea16ba9afc50e18dbdb222ea599b5fe
BLAKE2b-256 checksum
How to use checksums
640a334c4b2f758b264ee5735819c15c4977e4ce03dcfd267718acc3c01bf9ca
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for llama-index-tools-python-file 0.6.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page